Message-ID: <alpine.LFD.2.00.1102161142180.4744@dhcp-27-109.brq.redhat.com>
Date:	Wed, 16 Feb 2011 11:42:30 +0100 (CET)
From:	Lukas Czerner <lczerner@...hat.com>
To:	Lukas Czerner <lczerner@...hat.com>
cc:	linux-ext4@...r.kernel.org, tytso@....EDU
Subject: Re: [PATCH 1/2] resize2fs: Add support for lazy itable
 initialization

On Tue, 1 Feb 2011, Lukas Czerner wrote:

> Lazy inode table initialization speeds up file system resize operation
> because we can let the inode tables uninitialized. For some time now the
> mke2fs has similar option and now, when we have in-kernel lazyinit
> implementation we can add this feature to the resize2fs as well.
> 
> This commit adds extended options '-E' to the resize2fs code along with
> the first extended option lazy_itable_init=n. With lazy_itable_init
> extended option one can instruct resize2fs to skip inode table
> initialization to significantly speed-up file system resize. If the
> option is omitted and the file system supports lazy inode table
> initialization it defaults to 1.

ping

> 
> Signed-off-by: Lukas Czerner <lczerner@...hat.com>
> ---
>  resize/main.c         |   68 +++++++++++++++++++++++++++++++-
>  resize/online.c       |    2 +-
>  resize/resize2fs.8.in |   20 +++++++++
>  resize/resize2fs.c    |  105 +++++++++++++++++++++++++++---------------------
>  resize/resize2fs.h    |    3 +-
>  5 files changed, 148 insertions(+), 50 deletions(-)
> 
> diff --git a/resize/main.c b/resize/main.c
> index 28a49ba..0f1a8db 100644
> --- a/resize/main.c
> +++ b/resize/main.c
> @@ -40,7 +40,8 @@ char *program_name, *device_name, *io_options;
>  static void usage (char *prog)
>  {
>  	fprintf (stderr, _("Usage: %s [-d debug_flags] [-f] [-F] [-M] [-P] "
> -			   "[-p] device [new_size]\n\n"), prog);
> +			   "[-p] [-E extended_options] device [new_size]\n\n"),
> +			   prog);
>  
>  	exit (1);
>  }
> @@ -146,6 +147,59 @@ static void determine_fs_stride(ext2_filsys fs)
>  #endif
>  }
>  
> +static void parse_extended_opts(int *flags, const char *opts)
> +{
> +	char	*buf, *token, *next, *p, *arg, *badopt = 0;
> +	int	len;
> +	int	r_usage = 0;
> +
> +	len = strlen(opts);
> +	buf = malloc(len+1);
> +	if (!buf) {
> +		fprintf(stderr,
> +			_("Couldn't allocate memory to parse options!\n"));
> +		exit(1);
> +	}
> +	strcpy(buf, opts);
> +	for (token = buf; token && *token; token = next) {
> +		p = strchr(token, ',');
> +		next = 0;
> +		if (p) {
> +			*p = 0;
> +			next = p+1;
> +		}
> +		arg = strchr(token, '=');
> +		if (arg) {
> +			*arg = 0;
> +			arg++;
> +		}
> +		if (!strcmp(token, "lazy_itable_init")) {
> +			int lazy;
> +			if (arg)
> +				lazy = strtoul(arg, &p, 0);
> +			else
> +				lazy = 1;
> +			if (lazy)
> +				*flags |= RESIZE_LAZY_ITABLE_INIT;
> +		} else {
> +			r_usage++;
> +			badopt = token;
> +		}
> +	}
> +	if (r_usage) {
> +		fprintf(stderr, _("\nBad option(s) specified: %s\n\n"
> +			"Extended options are separated by commas, "
> +			"and may take an argument which\n"
> +			"\tis set off by an equals ('=') sign.\n\n"
> +			"Valid extended options are:\n"
> +			"\tlazy_itable_init=<0 to disable, 1 to enable>\n\n"),
> +			badopt ? badopt : "");
> +		free(buf);
> +		exit(1);
> +	}
> +	free(buf);
> +}
> +
>  int main (int argc, char ** argv)
>  {
>  	errcode_t	retval;
> @@ -174,6 +228,7 @@ int main (int argc, char ** argv)
>  	long		sysval;
>  	int		len, mount_flags;
>  	char		*mtpt;
> +	char *		extended_opts = NULL;
>  
>  #ifdef ENABLE_NLS
>  	setlocale(LC_MESSAGES, "");
> @@ -189,7 +244,7 @@ int main (int argc, char ** argv)
>  	if (argc && *argv)
>  		program_name = *argv;
>  
> -	while ((c = getopt (argc, argv, "d:fFhMPpS:")) != EOF) {
> +	while ((c = getopt (argc, argv, "d:fFhMPpS:E:")) != EOF) {
>  		switch (c) {
>  		case 'h':
>  			usage(program_name);
> @@ -215,6 +270,9 @@ int main (int argc, char ** argv)
>  		case 'S':
>  			use_stride = atoi(optarg);
>  			break;
> +		case 'E':
> +			extended_opts = optarg;
> +			break;
>  		default:
>  			usage(program_name);
>  		}
> @@ -232,6 +290,12 @@ int main (int argc, char ** argv)
>  	if (io_options)
>  		*io_options++ = 0;
>  
> +	if (access("/sys/fs/ext4/features/lazy_itable_init", R_OK) == 0)
> +		flags |= RESIZE_LAZY_ITABLE_INIT;
> +
> +	if (extended_opts)
> +		parse_extended_opts(&flags, extended_opts);
> +
>  	/*
>  	 * Figure out whether or not the device is mounted, and if it is
>  	 * where it is mounted.
> diff --git a/resize/online.c b/resize/online.c
> index 1d8d4ec..7bc27b3 100644
> --- a/resize/online.c
> +++ b/resize/online.c
> @@ -104,7 +104,7 @@ errcode_t online_resize_fs(ext2_filsys fs, const char *mtpt,
>  	 * but at least it allows on-line resizing to function.
>  	 */
>  	new_fs->super->s_feature_incompat &= ~EXT4_FEATURE_INCOMPAT_FLEX_BG;
> -	retval = adjust_fs_info(new_fs, fs, 0, *new_size);
> +	retval = adjust_fs_info(new_fs, fs, 0, *new_size, 0);
>  	if (retval)
>  		return retval;
>  
> diff --git a/resize/resize2fs.8.in b/resize/resize2fs.8.in
> index e02345d..448265c 100644
> --- a/resize/resize2fs.8.in
> +++ b/resize/resize2fs.8.in
> @@ -18,6 +18,10 @@ resize2fs \- ext2/ext3/ext4 file system resizer
>  .B \-S
>  .I RAID-stride
>  ]
> +[
> +.B \-E
> +.I extended-options
> +]
>  .I device
>  [
>  .I size
> @@ -128,6 +132,22 @@ The
>  program will heuristically determine the RAID stride that was specified
>  when the filesystem was created.  This option allows the user to
>  explicitly specify a RAID stride setting to be used by resize2fs instead.
> +.TP
> +.B \-E \fIextended-options
> +Set extended options for the filesystem.  Extended options are comma
> +separated, and may take an argument using the equals ('=') sign.
> +The following extended options are supported:
> +.RS 1.2i
> +.TP
> +.B lazy_itable_init\fR[\fB= \fI<0 to disable, 1 to enable>\fR]
> +If enabled and the uninit_bg feature is enabled, the inode table will
> +not be fully initialized by
> +.BR resize2fs .
> +This speeds up filesystem
> +resize noticeably, but it requires the kernel to finish
> +initializing the filesystem in the background when the filesystem is
> +mounted.  If the option value is omitted, it defaults to 1 to
> +enable lazy inode table initialization.
>  .SH KNOWN BUGS
>  The minimum size of the filesystem as estimated by resize2fs may be
>  incorrect, especially for filesystems with 1k and 2k blocksizes.
> diff --git a/resize/resize2fs.c b/resize/resize2fs.c
> index 216a626..1101364 100644
> --- a/resize/resize2fs.c
> +++ b/resize/resize2fs.c
> @@ -41,7 +41,8 @@
>  #endif
>  
>  static void fix_uninit_block_bitmaps(ext2_filsys fs);
> -static errcode_t adjust_superblock(ext2_resize_t rfs, blk64_t new_size);
> +static errcode_t adjust_superblock(ext2_resize_t rfs, blk64_t new_size,
> +				   int flags);
>  static errcode_t blocks_to_move(ext2_resize_t rfs);
>  static errcode_t block_mover(ext2_resize_t rfs);
>  static errcode_t inode_scan_and_fix(ext2_resize_t rfs);
> @@ -102,7 +103,7 @@ errcode_t resize_fs(ext2_filsys fs, blk64_t *new_size, int flags,
>  	if (retval)
>  		goto errout;
>  
> -	retval = adjust_superblock(rfs, *new_size);
> +	retval = adjust_superblock(rfs, *new_size, flags);
>  	if (retval)
>  		goto errout;
>  
> @@ -288,7 +289,8 @@ static void free_gdp_blocks(ext2_filsys fs,
>   * filesystem.
>   */
>  errcode_t adjust_fs_info(ext2_filsys fs, ext2_filsys old_fs,
> -			 ext2fs_block_bitmap reserve_blocks, blk64_t new_size)
> +			 ext2fs_block_bitmap reserve_blocks, blk64_t new_size,
> +			 int flags)
>  {
>  	errcode_t	retval;
>  	blk64_t		overhead = 0;
> @@ -497,8 +499,12 @@ retry:
>  		adjblocks = 0;
>  
>  		ext2fs_bg_flags_zap(fs, i);
> -		if (csum_flag)
> +		if (csum_flag && (flags & RESIZE_LAZY_ITABLE_INIT))
> +			ext2fs_bg_flags_set(fs, i, EXT2_BG_INODE_UNINIT);
> +		else if (csum_flag)
>  			ext2fs_bg_flags_set(fs, i, EXT2_BG_INODE_UNINIT | EXT2_BG_INODE_ZEROED);
> +		else
> +			flags &= ~RESIZE_LAZY_ITABLE_INIT;
>  		if (i == fs->group_desc_count-1) {
>  			numblocks = (ext2fs_blocks_count(fs->super) -
>  				     fs->super->s_first_data_block) %
> @@ -562,18 +568,57 @@ errout:
>  	return (retval);
>  }
>  
> +static errcode_t write_inode_tables(ext2_resize_t rfs, ext2_filsys fs)
> +{
> +	unsigned long	i, max_group;
> +	errcode_t	retval;
> +	int		adj = 0;
> +
> +	memset(rfs->itable_buf, 0, fs->blocksize * fs->inode_blocks_per_group);
> +	adj = rfs->old_fs->group_desc_count;
> +	max_group = fs->group_desc_count - adj;
> +	if (rfs->progress) {
> +		retval = rfs->progress(rfs, E2_RSZ_EXTEND_ITABLE_PASS,
> +				       0, max_group);
> +		if (retval)
> +			goto out;
> +	}
> +
> +	for (i = rfs->old_fs->group_desc_count;
> +	     i < fs->group_desc_count; i++) {
> +		/*
> +		 * Write out the new inode table
> +		 */
> +		retval = io_channel_write_blk64(fs->io,
> +						ext2fs_inode_table_loc(fs, i),
> +						fs->inode_blocks_per_group,
> +						rfs->itable_buf);
> +		if (retval)
> +			break;
> +
> +		io_channel_flush(fs->io);
> +		if (rfs->progress) {
> +			retval = rfs->progress(rfs, E2_RSZ_EXTEND_ITABLE_PASS,
> +					       i - adj + 1, max_group);
> +			if (retval)
> +				break;
> +		}
> +	}
> +	io_channel_flush(fs->io);
> +out:
> +	return retval;
> +}
> +
> +
>  /*
>   * This routine adjusts the superblock and other data structures, both
>   * in disk as well as in memory...
>   */
> -static errcode_t adjust_superblock(ext2_resize_t rfs, blk64_t new_size)
> +static errcode_t adjust_superblock(ext2_resize_t rfs, blk64_t new_size,
> +				   int flags)
>  {
> -	ext2_filsys fs;
> -	int		adj = 0;
> +	ext2_filsys	fs;
>  	errcode_t	retval;
> -	blk64_t		group_block;
> -	unsigned long	i;
> -	unsigned long	max_group;
>  
>  	fs = rfs->new_fs;
>  	ext2fs_mark_super_dirty(fs);
> @@ -585,7 +630,8 @@ static errcode_t adjust_superblock(ext2_resize_t rfs, blk64_t new_size)
>  	if (retval)
>  		return retval;
>  
> -	retval = adjust_fs_info(fs, rfs->old_fs, rfs->reserve_blocks, new_size);
> +	retval = adjust_fs_info(fs, rfs->old_fs, rfs->reserve_blocks, new_size,
> +				flags);
>  	if (retval)
>  		goto errout;
>  
> @@ -626,41 +672,8 @@ static errcode_t adjust_superblock(ext2_resize_t rfs, blk64_t new_size)
>  	if (retval)
>  		goto errout;
>  
> -	memset(rfs->itable_buf, 0, fs->blocksize * fs->inode_blocks_per_group);
> -	group_block = fs->super->s_first_data_block +
> -		rfs->old_fs->group_desc_count * fs->super->s_blocks_per_group;
> -
> -	adj = rfs->old_fs->group_desc_count;
> -	max_group = fs->group_desc_count - adj;
> -	if (rfs->progress) {
> -		retval = rfs->progress(rfs, E2_RSZ_EXTEND_ITABLE_PASS,
> -				       0, max_group);
> -		if (retval)
> -			goto errout;
> -	}
> -	for (i = rfs->old_fs->group_desc_count;
> -	     i < fs->group_desc_count; i++) {
> -		/*
> -		 * Write out the new inode table
> -		 */
> -		retval = io_channel_write_blk64(fs->io,
> -						ext2fs_inode_table_loc(fs, i),
> -						fs->inode_blocks_per_group,
> -						rfs->itable_buf);
> -		if (retval) goto errout;
> -
> -		io_channel_flush(fs->io);
> -		if (rfs->progress) {
> -			retval = rfs->progress(rfs, E2_RSZ_EXTEND_ITABLE_PASS,
> -					       i - adj + 1, max_group);
> -			if (retval)
> -				goto errout;
> -		}
> -		group_block += fs->super->s_blocks_per_group;
> -	}
> -	io_channel_flush(fs->io);
> -	retval = 0;
> -
> +	if (!(flags & RESIZE_LAZY_ITABLE_INIT))
> +		retval = write_inode_tables(rfs, fs);
>  errout:
>  	return retval;
>  }
> diff --git a/resize/resize2fs.h b/resize/resize2fs.h
> index 2184759..a968071 100644
> --- a/resize/resize2fs.h
> +++ b/resize/resize2fs.h
> @@ -79,6 +79,7 @@ typedef struct ext2_sim_progress *ext2_sim_progmeter;
>  
>  #define RESIZE_PERCENT_COMPLETE		0x0100
>  #define RESIZE_VERBOSE			0x0200
> +#define RESIZE_LAZY_ITABLE_INIT		0x0400	/* Do not initialize inode tables*/
>  
>  /*
>   * The core state structure for the ext2 resizer
> @@ -129,7 +130,7 @@ extern errcode_t resize_fs(ext2_filsys fs, blk64_t *new_size, int flags,
>  
>  extern errcode_t adjust_fs_info(ext2_filsys fs, ext2_filsys old_fs,
>  				ext2fs_block_bitmap reserve_blocks,
> -				blk64_t new_size);
> +				blk64_t new_size, int flags);
>  extern blk64_t calculate_minimum_resize_size(ext2_filsys fs);
>  
>  
> 

-- 
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists